Intelligent Systems and Control: Principles and Applications

Paperback | October 1, 2009

byLaxmidhar Behera, Indrani Kar

not yet rated|write a review
Intelligent Systems and Control: Principles and Applications is a textbook for undergraduate level courses on intelligent control, intelligent systems, adaptive control, and non-linear control. The book covers primers in neural networks, fuzzy logic, and non-linear control so that readers caneasily follow intelligent control techniques. Design principles for fuzzy and neural control schemes have been enumerated with an easy understanding for readers. Stability analysis of control systems have been provided with rigour. Intelligent control systems have been simulated for benchmarknon-linear systems across disciplines such as electrical system, electro-mechanical systems, and process control systems. Details of real-time experiments for cart-pole inverted pendulum system and seven degrees of freedom (DOF) robot manipulator using intelligent control schemes have been includedin the book to illustrate efficacy of these advanced control schemes. A chapter on quantum neural networks and its application has been included to illustrate the importance of the emerging research in quantum computational intelligence in control. Many examples with Matlab codes have been providedfor readers to comprehend the subject matter provided in this book. Each chapter includes a set of exercise problems for readers to get well-versed with the subject. C-codes for selected exercise problems have been included in the CD accompanying the book. Simulation results and experimental videos are also included in the CD. This book can be used as a referencefor courses such as Artificial Neural Networks and Fuzzy Logic, Artificial Intelligence, Instrumentation and Control, and Advanced Control Systems. Also practicing engineers in RandD sectors will be greatly benefitted from this book.

Pricing and Purchase Info

$41.50

Ships within 1-3 weeks
Ships free on orders over $25

From the Publisher

Intelligent Systems and Control: Principles and Applications is a textbook for undergraduate level courses on intelligent control, intelligent systems, adaptive control, and non-linear control. The book covers primers in neural networks, fuzzy logic, and non-linear control so that readers caneasily follow intelligent control techniques...

Dr Laxmidhar Behera is currently Associate Professor in the Department of Electrical Engineering at IIT Kanpur. He has recently joined ISRC, UUM as a reader on a sabatical from IIT Kanpur. A Ph D from IIT Delhi, he has worked as Assistant Professor in BITS Pilani during 1995-1999 and pursued his post-doctoral studies in German Nationa...
Format:PaperbackDimensions:496 pagesPublished:October 1, 2009Publisher:Oxford University PressLanguage:English

The following ISBNs are associated with this title:

ISBN - 10:0198063156

ISBN - 13:9780198063155

Customer Reviews of Intelligent Systems and Control: Principles and Applications

Reviews

Extra Content

Table of Contents

1. Nonlinear Control: Primer1.1 Norms of Signals, Vectors and Matrices1.2 Positive Definite Functions1.3 Positive Definite Matrices1.4 Continuous-time State-space Model1.4.1 LTI State-space Model1.5 Nonlinear State-space model1.5.1 Equilibrium point and Linearization using first order Taylor series1.5.2 Linearization technique for operating points other than origin1.6 Lyapunov Stability Theory1.6.1 Lyapunov stability of time invariant system1.6.2 LaSalle's Invariance Theorem1.6.3 Chetaev's Instability Theorem1.6.4 Lyapunov stability of time varying system1.6.5 Lyapunov's indirect method1.6.6 Lyapunov stability for linear systems1.7 Discrete-time Systems1.7.1 Discrete-time LTI State-space Model1.7.2 Discrete-time Nonlinear State-space model1.7.3 ARMAX and NARMAX Models1.7.4 Lyapunov Stability for Discrete Time Systems1.8 Modeling of Different Nonlinear Systems1.8.1 Inertial Wheel Pendulum1.8.2 Two Link Manipulator1.8.3 Inverted Pendulum Mounted on A Cart1.8.4 Induction Motor1.9 Nonlinear Control Strategies1.9.1 Feedback Linearization1.9.2 Back-stepping Design1.9.3 State-feedback linearizable systems1.10 Summary1.11 Exercises2. Neural Networks2.1 Feed-Forward Networks2.2 Multi-layered Neural Networks2.2.1 Principle of Gradient Descent2.2.2 Derivation of Back Propagation Algorithm2.2.3 Generalized Delta Rule2.2.4 Convergence of BP Learning Algorithm2.2.5 Variations in Back Propagation Algorithm2.3 Radial Basis Function Networks2.3.1 Radial Basis Functions2.3.2 Learning in RBFN2.4 Adaptive Learning Rate2.4.1 Lyapunov function based adaptive learning rate2.5 Feedback Networks2.5.1 Response of Recurrent Networks2.5.2 Learning Algorithms2.5.3 Back Propagation Through Time (BPTT)2.5.4 Real Time Recurrent Learning (RTRL)2.6 Kohonen Self Organizing Map2.7 System Identification Using Neural Networks2.8 SOM based Identification2.9 Summary2.10 Exercises3. Fuzzy Logic 1133.1 Classical sets3.1.1 Operations on classical sets3.2 Fuzzy Sets3.2.1 Concept of a fuzzy number3.2.2 Operations on Fuzzy sets3.2.3 Other Fuzzy Operations3.2.4 Properties of Fuzzy Sets3.2.5 Some Typical Membership Functions3.2.6 Fuzzy Membership vs. Probability3.2.7 Extension Principle of Fuzzy Sets3.2.8 Crisp Relation3.2.9 Fuzzy Relations3.2.10 Projection of Fuzzy Relations3.2.11 Cylindrical Extension of Fuzzy Relations3.2.12 Relation Inference3.3 Fuzzy Rule Base and Approximate Reasoning3.3.1 Fuzzy Linguistic Variables3.3.2 Linguistic modifier3.3.3 Rule-base systems3.3.4 Fuzzy Rule-base3.3.5 Fuzzy Implication Relations3.3.6 Fuzzy Compositional Rules3.3.7 Inference mechanism compared3.3.8 Approximate Reasoning3.4 Fuzzy Logic Control (FLC)3.4.1 Mamdani Model3.4.2 Takagi-Sugeno (T-S) Fuzzy Model3.5 System Identification Using T-S Fuzzy Models3.5.1 The T-S Model From Input-Output Data3.5.2 The T-S Fuzzy Model Using Linearization3.6 Summary3.7 Exercises4. Indirect Adaptive Control Using Neural Networks4.1 Continuous Time Affine Systems4.1.1 Model Identification4.1.2 Controller design4.2 Discrete Time Affine Systems4.2.1 Model Identification4.2.2 Controller Design4.3 Discrete Time Non-affine System4.3.1 Model Identification4.3.2 Controller Design: Traditional NN approach4.3.3 Controller Design: Network Inversion4.4 Summary4.5 Appendix4.5.1 Recursive Least Squares4.6 Exercises5. Direct Adaptive Control Using Neural Networks5.1 Direct Adaptive Control5.2 Single Input Single Output Affine Systems5.2.1 f(x) is unknown but g(x) is known5.2.2 f(x) and g(x) both are unknown5.3 Multi Input Multi Output Systems5.4 Single Input Single Output Discrete Time Affine Systems5.4.1 f(x) is unknown but g(x) is known5.4.2 f(x) and g(x) both are unknown5.5 Back-stepping Control5.5.1 System Description5.5.2 Traditional Back-stepping Design5.5.3 Robust Back-stepping controller design using RBFN5.5.4 Back-stepping Control for A Robot Manipulator5.6 Summary5.7 Exercises6. Approximate Dynamic Programming6.1 Linear Quadratic Regulator6.2 The HJB Formulation6.3 HJB for Affine Systems6.4 HDP and DHP6.5 Single Network Adaptive Critic6.6 Continuous time Adaptive Critic6.7 Adaptive Critic Using T-S fuzzy Model6.7.1 Continuous time adaptive critic6.7.2 Discrete time adaptive critic6.8 Summary6.9 Exercises7. Fuzzy Logic Control7.1 Construction of an FLC7.2 Fuzzy PD Controller7.2.1 The rule base7.2.2 Membership function7.2.3 Fuzzy Parameter Optimization7.2.4 Rule Generation Using Optimization Technique7.3 Fuzzy PI Controller7.3.1 The rule base for the Fuzzy PI Controller7.3.2 Membership function7.3.3 Parameter Optimization and Rule Generation Using UMDA7.4 Fuzzy PI Controller for a Series DC Motor7.4.1 Parameter Optimization and Rule Generation7.5 FLC using Lyapunov Synthesis7.5.1 Rotational Translational Proof-Mass Actuator7.6 Horizontal Planar Two Link Robot Manipulator7.6.1 Arm Posture7.6.2 Elbow Control7.6.3 Controller Design7.7 Summary7.8 Appendix7.8.1 Genetic Algorithm (GA)7.9 Exercises8. Takagi-Sugeno Fuzzy Model Based Control8.1 T-S Fuzzy model8.2 Linear Matrix Inequality (LMI) Technique8.2.1 Common Lyapunov Matrix Criterion for stability of the T-S model8.2.2 Parallel Distributed Fuzzy Compensator8.3 Fixed gain state feedback controller design technique8.3.1 Fixed gain state feedback controller8.4 Variable gain controller design using single linear nominal plant8.4.1 The Control Problem8.4.2 Variable Gain Controller - I8.5 Variable gain controller design using each linear subsystem as nominal plant8.5.1 The Control Problem8.5.2 Variable Gain Controller - II8.6 Controller design using discrete T-S fuzzy system8.6.1 Linear state feedback controller for discrete T-S fuzzy system8.7 Summary8.8 Appendix8.9 Exercises9. Intelligent Control of a Pendulum on a Cart9.1 T-S fuzzy model representation9.2 Control Using T-S Fuzzy Model9.3 Network Inversion Based Control9.3.1 Continuous-time Iterative Update9.3.2 Discrete-time Update9.4 T-S fuzzy Controller9.4.1 Continuous time weight update law9.4.2 Discrete Time Weight Update Law9.5 Cart Pole System: Simulation and Experiment9.5.1 T-S Fuzzy model of the Cart-Pole9.5.2 Control Systems Design9.5.3 Experiment on a Cart Pole System9.6 Summary9.7 Exercises10. Visual Motor Control of a Redundant Manipulator10.1 System Model10.1.1 Experimental Setup10.1.2 The Manipulator Model10.1.3 The Camera Model10.2 Visual Motor Control Using Neural Networks10.2.1 Visual Motor control with KSOM10.2.2 Simulation and Experimental Results10.2.3 Network Architecture and Workspace dimensions10.2.4 Training10.2.5 Testing10.2.6 Real-Time Experiment10.3 Visual Motor Control using a Fuzzy Network10.3.1 Fuzzy C-mean Clustering10.3.2 Multi-step incremental Learning10.3.3 Simulation and Experimental Results10.3.4 VMC using Incremental Learning10.4 SummaryA List of C Programs on CD